Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates and time-related terms

    oai_token-act-pair · gpt-3.5-turbo

    temporal expressions and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.84
    artisan
    -0.83
     kindred
    -0.78
    urities
    -0.76
    zech
    -0.76
    oyal
    -0.75
     Cosponsors
    -0.72
    rotein
    -0.70
    apons
    -0.69
    olen
    -0.67
    POSITIVE LOGITS
     elapsed
    1.15
     timeframe
    1.14
    chron
    1.12
     calendars
    1.09
     shortest
    1.09
     calendar
    1.07
     shortened
    1.05
     leng
    1.03
     clock
    1.02
     clocks
    1.00
    Act Density 0.714%

    No Known Activations